Do honeybees have an innate MNL?

Step1. download packages

required packages

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ tibble  3.1.5     ✓ purrr   0.3.4
## ✓ tidyr   1.1.4     ✓ stringr 1.4.0
## ✓ readr   2.0.2     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(stringr)
library(wesanderson)

Step 2. Clean Up Data

Horizontal Test (Left/Right)

dat3 <- read.csv("~/Documents/GitHub/honours-project/1-42 LR.csv")
dat3$bee_id <- as.factor(dat3$bee_id)
dat3$number <- as.factor(dat3$number)



# Split the data into 2 groups: small/ big
dat3.small <- dat3 %>% 
  filter(dat3$number == "small")
dat3.big <- dat3 %>% 
  filter(dat3$number == "large")

# add a new column or LR
dat3.small.LR <- dat3.small %>% 
  mutate(LR = ifelse(str_detect(choice, "1"), "L", "R")) # Create a new column for S/B
dat3.big.LR <- dat3.big %>% 
  mutate(LR = ifelse(str_detect(choice, "1"), "L", "R"))

# split into small L/R and big L/R
dat3.small.L <- dat3.small.LR %>%  # small L
  filter(dat3.small.LR$LR == "L")
  
dat3.small.L.prop <- dat3.small.L %>% # small L proportion for individual
  group_by(bee_id) %>% 
  summarise(prop = length(LR)/10)
as.numeric(unlist(dat3.small.L.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0
## [16] 16.0 17.0 18.0 19.0 20.0 21.0 22.0 23.0 24.0 25.0 26.0 27.0 28.0 29.0 30.0
## [31] 31.0 32.0 33.0 34.0 35.0 36.0 37.0 38.0 39.0 40.0 41.0 42.0  0.3  0.3  0.6
## [46]  0.7  0.4  0.3  0.6  0.7  0.7  0.5  0.5  0.7  0.2  0.5  0.5  0.2  0.3  0.4
## [61]  0.4  0.2  0.3  0.3  0.2  0.7  0.8  0.6  0.8  0.3  0.7  0.5  0.2  0.7  0.7
## [76]  0.5  0.2  0.4  0.9  0.3  0.4  0.6  0.1  0.7

small.L.mean <- mean(dat3.small.L.prop$prop) # mean for small L
small.L.sd <- sd(dat3.small.L.prop$prop) # sd for small L

dat3.small.R <- dat3.small.LR %>%  # small R
  filter(dat3.small.LR$LR == "R")

dat3.small.R.prop <- dat3.small.R %>% # small R proportion for individual
  group_by(bee_id) %>% 
  summarise(prop = length(LR)/10)
as.numeric(unlist(dat3.small.R.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0
## [16] 16.0 17.0 18.0 19.0 20.0 21.0 22.0 23.0 24.0 25.0 26.0 27.0 28.0 29.0 30.0
## [31] 31.0 32.0 33.0 34.0 35.0 36.0 37.0 38.0 39.0 40.0 41.0 42.0  0.7  0.7  0.4
## [46]  0.3  0.6  0.7  0.4  0.3  0.3  0.5  0.5  0.3  0.8  0.5  0.5  0.8  0.7  0.6
## [61]  0.6  0.8  0.7  0.7  0.8  0.3  0.2  0.4  0.2  0.7  0.3  0.5  0.8  0.3  0.3
## [76]  0.5  0.8  0.6  0.1  0.7  0.6  0.4  0.9  0.3

small.R.mean <- mean(dat3.small.R.prop$prop) # mean for small R
small.R.sd <- sd(dat3.small.R.prop$prop) # sd for small R

### BIG ###
dat3.big.L <- dat3.big.LR %>%  # big L
  filter(dat3.big.LR$LR == "L")

dat3.big.L.prop <- dat3.big.L %>% # big L proportion for individual
  group_by(bee_id) %>% 
  summarise(prop = length(LR)/10)
as.numeric(unlist(dat3.big.L.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 14.0 15.0 16.0
## [16] 17.0 18.0 19.0 20.0 21.0 22.0 23.0 24.0 25.0 26.0 27.0 28.0 29.0 30.0 31.0
## [31] 32.0 34.0 35.0 36.0 37.0 38.0 39.0 40.0 41.0 42.0  0.3  0.4  0.5  0.5  0.3
## [46]  0.5  0.6  0.5  0.6  0.6  0.5  0.5  0.4  0.3  0.3  0.3  0.2  0.4  0.4  0.1
## [61]  0.2  0.3  0.3  0.5  0.5  0.5  0.1  0.5  0.3  0.5  0.1  0.3  0.2  0.3  0.3
## [76]  0.2  0.3  0.3  0.1  0.4

big.L.mean <- mean(dat3.big.L.prop$prop) # mean for big L
big.L.sd <- sd(dat3.big.L.prop$prop) # sd for big L

dat3.big.R <- dat3.big.LR %>%  # big R
  filter(dat3.big.LR$LR == "R")

dat3.big.R.prop <- dat3.big.R %>% # big R proportion for individual
  group_by(bee_id) %>% 
  summarise(prop = length(LR)/10)
as.numeric(unlist(dat3.big.R.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0
## [16] 16.0 17.0 18.0 19.0 20.0 21.0 22.0 23.0 24.0 25.0 26.0 27.0 28.0 29.0 30.0
## [31] 31.0 32.0 33.0 34.0 35.0 36.0 37.0 38.0 39.0 40.0 41.0 42.0  0.7  0.6  0.5
## [46]  0.5  0.7  0.5  0.4  0.5  0.4  0.4  0.5  0.5  1.0  0.6  0.7  0.7  0.7  0.8
## [61]  0.6  0.6  0.9  0.8  0.7  0.7  0.5  0.5  0.5  0.9  0.5  0.7  0.5  0.9  1.0
## [76]  0.7  0.8  0.7  0.7  0.8  0.7  0.7  0.9  0.6

big.R.mean <- mean(dat3.big.R.prop$prop) # mean for big R
big.R.sd <- sd(dat3.big.R.prop$prop) # sd for big R

Horizontal Test (Up/Down)

dat4 <- read.csv("~/Documents/GitHub/honours-project/28-42 UD.csv")
dat4$BEEID <- as.factor(dat4$BEEID)
dat4$NUMBER <- as.factor(dat4$NUMBER)


dat4$UD <- ifelse(str_detect(dat4$CHOICE, "1"), "U", "D")
# Split the data into 2 groups: small/ big
dat4.small <- dat4 %>% 
  filter(dat4$NUMBER == "small")
dat4.big <- dat4 %>% 
  filter(dat4$NUMBER == "large")

# split into small L/R and big L/R
dat4.small.U <- dat4.small %>%  # small U
  filter(UD == "U")

dat4.small.U.prop <- dat4.small.U %>% # small U proportion for individual
  group_by(BEEID) %>% 
  summarise(prop = length(UD)/10)
as.numeric(unlist(dat4.small.U.prop))

##  [1]  1.0  2.0  3.0  4.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0  0.5
## [16]  0.7  0.2  0.9  0.5  0.2  0.4  0.7  0.8  0.6  0.1  0.5  0.8  0.8

small.U.mean <- mean(dat4.small.U.prop$prop) # mean for small U
small.U.sd <- sd(dat4.small.U.prop$prop) # sd for small U

#------------------------------------------#

dat4.small.D <- dat4.small %>%  # small D
  filter(UD == "D")

dat4.small.D.prop <- dat4.small.D %>% # small D proportion for individual
  group_by(BEEID) %>% 
  summarise(prop = length(UD)/10)
as.numeric(unlist(dat4.small.D.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0
## [16]  0.5  0.3  0.8  0.1  1.0  0.5  0.8  0.6  0.3  0.2  0.4  0.9  0.5  0.2  0.2

small.D.mean <- mean(dat4.small.D.prop$prop) # mean for small D
small.D.sd <- sd(dat4.small.D.prop$prop) # sd for small D

#-----------------------------------------#

dat4.big.U <- dat4.big %>%  # big U
  filter(UD == "U")

dat4.big.U.prop <- dat4.big.U %>% # bog U proportion for individual
  group_by(BEEID) %>% 
  summarise(prop = length(UD)/10)
as.numeric(unlist(dat4.big.U.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0
## [16]  0.8  0.9  0.3  0.7  0.3  0.5  0.9  0.3  0.4  0.8  0.6  0.3  0.1  0.7  0.3

big.U.mean <- mean(dat4.big.U.prop$prop) # mean for big U
big.U.sd <- sd(dat4.big.U.prop$prop) # sd for big U

#---------------------------------------#
dat4.big.D <- dat4.big %>%  # small D
  filter(UD == "D")

dat4.big.D.prop <- dat4.big.D %>% # small D proportion for individual
  group_by(BEEID) %>% 
  summarise(prop = length(UD)/10)
as.numeric(unlist(dat4.big.D.prop))

##  [1]  1.0  2.0  3.0  4.0  5.0  6.0  7.0  8.0  9.0 10.0 11.0 12.0 13.0 14.0 15.0
## [16]  0.2  0.1  0.7  0.3  0.7  0.5  0.1  0.7  0.6  0.2  0.4  0.7  0.9  0.3  0.7

big.D.mean <- mean(dat4.big.D.prop$prop) # mean for small D
big.D.sd <- sd(dat4.big.D.prop$prop) # sd for small D

Plot Barplots

The percentage of choosing L/R

## data for plotting bar plot
R <- data.frame(number = rep(c("small","big"), each = 2), 
           direction = rep(c("L","R"), times = 2),
           proportion = c(0.50,0.50, 0.29,0.71),
           mean = c(small.L.mean, small.R.mean, big.L.mean, big.R.mean),
           sd = c(small.L.sd, small.R.sd, big.L.sd, big.R.sd))
# barplot
exp1.LR <- ggplot(R, aes(x = number, y = proportion, fill = direction)) +
  geom_bar(stat = "identity", position = "dodge") + 
  geom_errorbar(aes(ymin = mean-sd, ymax = mean+sd), width=.2,
                position=position_dodge(.9)) + 
  scale_y_continuous(labels = scales::percent_format(accuracy = 1, suffix = NULL), limits = c(0,1)) +
  geom_hline(yintercept = 0.5, linetype = "dashed", colour = "grey") +
  labs (x= "Number Tests", y = "Proportion of choosing L or R in two number tests") +
  scale_fill_manual(values = wes_palette("GrandBudapest1", n = 2)) +
  theme(panel.background = element_blank(),
        axis.line = element_line(colour = "black"))
print(exp1.LR)

The percentage of choosing U/D

## data for plotting bar plot
U <- data.frame(number = rep(c("small","big"), each = 2), 
                direction = rep(c("U","D"), times = 2),
                proportion = c(0.51,0.49, 0.53,0.47),
                mean = c(small.U.mean, small.D.mean, big.U.mean, big.D.mean),
                sd = c(small.U.sd, small.D.sd, big.U.sd, big.D.sd))
# barplot
ggplot(U, aes(x = number, y = proportion, fill = direction)) +
  geom_bar(stat = "identity", position = "dodge") + 
  geom_errorbar(aes(ymin = mean-sd, ymax = mean+sd), width=.2,
                position=position_dodge(.9)) + 
  scale_y_continuous(labels = scales::percent_format(accuracy = 1, suffix = NULL), limits = c(0,1)) +
  labs (x= "Number Tests", y = "Proportion of choosing U or D in two number tests") +
  scale_fill_manual(values = wes_palette("GrandBudapest2", n = 2)) +
  geom_hline(yintercept = 0.5, linetype = "dashed", colour = "grey") +
  theme(panel.background = element_blank(),
        axis.line = element_line(colour = "black"))

template provided by Bug of the week